The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep learning based entropy modeling methods generally assume the latent codes are statistically independent or depend on some side information or local context, which fails to take the global similarity within the context into account and thus hinder the accurate entropy estimation. To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context. Specifically, we first introduce the proxy similarity functions and spatial masks to handle the missing reference problem in context modeling. Then, we combine the local and the global context via a non-local attention block and employ it in masked convolutional networks for entropy modeling. The entropy model is further adopted as the rate loss in a joint rate-distortion optimization to guide the training of the analysis transform and the synthesis transform network in transforming coding framework. Considering that the width of the transforms is essential in training low distortion models, we finally produce a U-Net block in the transforms to increase the width with manageable memory consumption and time complexity. Experiments on Kodak and Tecnick datasets demonstrate the superiority of the proposed context-based non-local attention block in entropy modeling and the U-Net block in low distortion compression against the existing image compression standards and recent deep image compression models.
When training end-to-end learned models for lossy compression, one has to balance the rate and distortion losses. This is typically done by manually setting a tradeoff parameter $\beta$, an approach called $\beta$-VAE. Using this approach it is difficult to target a specific rate or distortion value, because the result can be very sensitive to $\beta$, and the appropriate value for $\beta$ depends on the model and problem setup. As a result, model comparison requires extensive per-model $\beta$-tuning, and producing a whole rate-distortion curve (by varying $\beta$) for each model to be compared. We argue that the constrained optimization method of Rezende and Viola, 2018 is a lot more appropriate for training lossy compression models because it allows us to obtain the best possible rate subject to a distortion constraint. This enables pointwise model comparisons, by training two models with the same distortion target and comparing their rate. We show that the method does manage to satisfy the constraint on a realistic image compression task, outperforms a constrained optimization method based on a hinge-loss, and is more practical to use for model selection than a $\beta$-VAE.
Fast and effective image compression for multi-dimensional images has become increasingly important for efficient storage and transfer of massive amounts of high-resolution images and videos. Desirable properties in compression methods include (1) high reconstruction quality at a wide range of compression rates while preserving key local details, (2) computational scalability, (3) applicability to a variety of different image/video types and of different dimensions, and (4) ease of tuning. We present such a method for multi-dimensional image compression called Compression via Adaptive Recursive Partitioning (CARP). CARP uses an optimal permutation of the image pixels inferred from a Bayesian probabilistic model on recursive partitions of the image to reduce its effective dimensionality, leading to a parsimonious representation that preserves information. CARP uses a multi-layer Bayesian hierarchical model to achieve self-tuning and regularization to avoid overfitting resulting in one single parameter to be specified by the user to attain the desired compression rate. Extensive numerical experiments using a variety of datasets including 2D ImageNet, 3D medical image, and real-life YouTube and surveillance videos show that CARP dominates the state-of-the-art compression approaches including JPEG, JPEG2000, MPEG4, and a neural network-based method for all of these different image types and often on nearly all of the individual images.
The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human quality judgments. Perceptual datasets gathered for this purpose have provided useful benchmarks for improving IQA methods, but their heavy use creates a risk of overfitting. Here, we perform a large-scale comparison of IQA models in terms of their use as objectives for the optimization of image processing algorithms. Specifically, we use eleven full-reference IQA models to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression. Subjective testing on the optimized images allows us to rank the competing models in terms of their perceptual performance, elucidate their relative advantages and disadvantages in these tasks, and propose a set of desirable properties for incorporation into future IQA models.
Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.
It plays a fundamental role to compactly represent the visual information towards the optimization of the ultimate utility in myriad visual data centered applications. With numerous approaches proposed to efficiently compress the texture and visual features serving human visual perception and machine intelligence respectively, much less work has been dedicated to studying the interactions between them. Here we investigate the integration of feature and texture compression, and show that a universal and collaborative visual information representation can be achieved in a hierarchical way. In particular, we study the feature and texture compression in a scalable coding framework, where the base layer serves as the deep learning feature and enhancement layer targets to perfectly reconstruct the texture. Based on the strong generative capability of deep neural networks, the gap between the base feature layer and enhancement layer is further filled with the feature level texture reconstruction, aiming to further construct texture representation from feature. As such, the residuals between the original and reconstructed texture could be further conveyed in the enhancement layer. To improve the efficiency of the proposed framework, the base layer neural network is trained in a multi-task manner such that the learned features enjoy both high quality reconstruction and high accuracy analysis. We further demonstrate the framework and optimization strategies in face image compression, and promising coding performance has been achieved in terms of both rate-fidelity and rate-accuracy.
The JPEG image compression algorithm is the most popular method of image compression because of its ability for large compression ratios. However, to achieve such high compression, information is lost. For aggressive quantization settings, this leads to a noticeable reduction in image quality. Artifact correction has been studied in the context of deep neural networks for some time, but the current state-of-the-art methods require a different model to be trained for each quality setting, greatly limiting their practical application. We solve this problem by creating a novel architecture which is parameterized by the JPEG files quantization matrix. This allows our single model to achieve state-of-the-art performance over models trained for specific quality settings.
We focus on the problem of training convolutional neural networks on gigapixel histopathology images to predict image-level targets. For this purpose, we extend Neural Image Compression (NIC), an image compression framework that reduces the dimensionality of these images using an encoder network trained unsupervisedly. We propose to train this encoder using supervised multitask learning (MTL) instead. We applied the proposed MTL NIC to two histopathology datasets and three tasks. First, we obtained state-of-the-art results in the Tumor Proliferation Assessment Challenge of 2016 (TUPAC16). Second, we successfully classified histopathological growth patterns in images with colorectal liver metastasis (CLM). Third, we predicted patient risk of death by learning directly from overall survival in the same CLM data. Our experimental results suggest that the representations learned by the MTL objective are: (1) highly specific, due to the supervised training signal, and (2) transferable, since the same features perform well across different tasks. Additionally, we trained multiple encoders with different training objectives, e.g. unsupervised and variants of MTL, and observed a positive correlation between the number of tasks in MTL and the system performance on the TUPAC16 dataset.
Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when dealing with sensitive personal data. To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service. With PrivEdge, each user independently uses their private data to locally train a one-class reconstructive adversarial network that succinctly represents their training data. As sending the model parameters to the service provider in the clear would reveal private information, PrivEdge secret-shares the parameters among two non-colluding MLaaS providers, to then provide cryptographically private prediction services through secure multi-party computation techniques. We quantify the benefits of PrivEdge and compare its performance with state-of-the-art centralised architectures on three privacy-sensitive image-based tasks: individual identification, writer identification, and handwritten letter recognition. Experimental results show that PrivEdge has high precision and recall in preserving privacy, as well as in distinguishing between private and non-private images. Moreover, we show the robustness of PrivEdge to image compression and biased training data. The source code is available at https://github.com/smartcameras/PrivEdge.
In recent years, neural network-based image compression techniques have been able to outperform traditional codecs and have opened the gates for the development of learning-based video codecs. However, to take advantage of the high temporal correlation in videos, more sophisticated architectures need to be employed. This paper presents PredEncoder, a hybrid video compression framework based on the concept of predictive auto-encoding that models the temporal correlations between consecutive video frames using a prediction network which is then combined with a progressive encoder network to exploit the spatial redundancies. A variable-rate block encoding scheme has been proposed in the paper that leads to remarkably high quality to bit-rate ratios. By joint training and fine-tuning of this hybrid architecture, PredEncoder has been able to gain significant improvement over the MPEG-4 codec and has achieved bit-rate savings over the H.264 codec in the low to medium bit-rate range for HD videos and comparable results over most bit-rates for non-HD videos. This paper serves to demonstrate how neural architectures can be leveraged to perform at par with the highly optimized traditional methodologies in the video compression domain.
Image compression with upsampling encodes information to succeedingly increase image resolution, for example by encoding differences in FUIF and JPEG XL. It is useful for progressive decoding, also often can improve compression ratio - both for lossless compression and e.g. DC coefficients of lossy. However, the currently used solutions rather do not exploit context dependence for encoding of such upscaling information. This article discusses simple inexpensive general techniques for this purpose, which allowed to save on average $0.645$ bits/difference (between $0.138$ and $1.489$) for the last upscaling for 48 standard $512\times 512$ grayscale 8 bit images - compared to assumption of fixed Laplace distribution. Using least squares linear regression of context to predict center of Laplace distribution gave on average $0.393$ bits/difference savings. The remaining savings were obtained by additionally predicting width of this Laplace distribution, also using just the least squares linear regression. For RGB images, optimization of color transform alone gave mean $\approx 4.6\%$ size reduction comparing to standard YCrCb if using fixed transform, $\approx 6.3\%$ if optimizing transform individually for each image. Then further mean $\approx 10\%$ reduction was obtained if predicting Laplace parameters based on context. The presented simple inexpensive general methodology can be also used for different types of data like DCT coefficients in lossy image compression.
We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless super-resolution. For lossless super-resolution, we predict the probability of a high-resolution image, conditioned on the low-resolution input, and use entropy coding to compress this super-resolution operator. Super-Resolution based Compression (SReC) is able to achieve state-of-the-art compression rates with practical runtimes on large datasets. Code is available online at https://github.com/caoscott/SReC.
Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there is still a performance gap between learned compression algorithms and reigning compression standards, especially in terms of widely used PSNR metric. In this paper, we explore the remaining redundancy of recent learned compression algorithms. We have found accurate entropy models for rate estimation largely affect the optimization of network parameters and thus affect the rate-distortion performance. Therefore, in this paper, we propose to use discretized Gaussian Mixture Likelihoods to parameterize the distributions of latent codes, which can achieve a more accurate and flexible entropy model. Besides, we take advantage of recent attention modules and incorporate them into network architecture to enhance the performance. Experimental results demonstrate our proposed method achieves a state-of-the-art performance compared to existing learned compression methods on both Kodak and high-resolution datasets. To our knowledge our approach is the first work to achieve comparable performance with latest compression standard Versatile Video Coding (VVC) regarding PSNR. More importantly, our approach generates more visually pleasant results when optimized by MS-SSIM. This project page is at this https URL https://github.com/ZhengxueCheng/Learned-Image-Compression-with-GMM-and-Attention
Computer vision tasks are often expected to be executed on compressed images. Classical image compression standards like JPEG 2000 are widely used. However, they do not account for the specific end-task at hand. Motivated by works on recurrent neural network (RNN)-based image compression and three-dimensional (3D) reconstruction, we propose unified network architectures to solve both tasks jointly. These joint models provide image compression tailored for the specific task of 3D reconstruction. Images compressed by our proposed models, yield 3D reconstruction performance superior as compared to using JPEG 2000 compression. Our models significantly extend the range of compression rates for which 3D reconstruction is possible. We also show that this can be done highly efficiently at almost no additional cost to obtain compression on top of the computation already required for performing the 3D reconstruction task.
We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual. We then model the distribution of the residual with a convolutional neural network-based probabilistic model that is conditioned on the BPG reconstruction, and combine it with entropy coding to losslessly encode the residual. Finally, the image is stored using the concatenation of the bitstreams produced by BPG and the learned residual coder. The resulting compression system achieves state-of-the-art performance in learned lossless full-resolution image compression, outperforming previous learned approaches as well as PNG, WebP, and JPEG2000.
The Object-Based Image Coding (OBIC) that was extensively studied about two decades ago, promised a vast application perspective for both ultra-low bitrate communication and high-level semantical content understanding, but it had rarely been used due to the inefficient compact representation of object with arbitrary shape. A fundamental issue behind is how to efficiently process the arbitrary-shaped objects at a fine granularity (e.g., feature element or pixel wise). To attack this, we have proposed to apply the element-wise masking and compression by devising an object segmentation network for image layer decomposition, and parallel convolution-based neural image compression networks to process masked foreground objects and background scene separately. All components are optimized in an end-to-end learning framework to intelligently weigh their (e.g., object and background) contributions for visually pleasant reconstruction. We have conducted comprehensive experiments to evaluate the performance on PASCAL VOC dataset at a very low bitrate scenario (e.g., $\lesssim$0.1 bits per pixel - bpp) which have demonstrated noticeable subjective quality improvement compared with JPEG2K, HEVC-based BPG and another learned image compression method. All relevant materials are made publicly accessible at https://njuvision.github.io/Neural-Object-Coding/.
Color and structure are the two pillars that construct an image. Usually, the structure is well expressed through a rich spectrum of colors, allowing objects in an image to be recognized by neural networks. However, under extreme limitations of color space, the structure tends to vanish, and thus a neural network might fail to understand the image. Interested in exploring this interplay between color and structure, we study the scientific problem of identifying and preserving the most informative image structures while constraining the color space to just a few bits, such that the resulting image can be recognized with possibly high accuracy. To this end, we propose a color quantization network, ColorCNN, which learns to structure the images from the classification loss in an end-to-end manner. Given a color space size, ColorCNN quantizes colors in the original image by generating a color index map and an RGB color palette. Then, this color-quantized image is fed to a pre-trained task network to evaluate its performance. In our experiment, with only a 1-bit color space (i.e., two colors), the proposed network achieves 82.1% top-1 accuracy on the CIFAR10 dataset, outperforming traditional color quantization methods by a large margin. For applications, when encoded with PNG, the proposed color quantization shows superiority over other image compression methods in the extremely low bit-rate regime. The code is available at: https://github.com/hou-yz/color_distillation.
Deep learning for computer vision depends on lossy image compression: it reduces the storage required for training and test data and lowers transfer costs in deployment. Mainstream datasets and imaging pipelines all rely on standard JPEG compression. In JPEG, the degree of quantization of frequency coefficients controls the lossiness: an 8 by 8 quantization table (Q-table) decides both the quality of the encoded image and the compression ratio. While a long history of work has sought better Q-tables, existing work either seeks to minimize image distortion or to optimize for models of the human visual system. This work asks whether JPEG Q-tables exist that are "better" for specific vision networks and can offer better quality--size trade-offs than ones designed for human perception or minimal distortion. We reconstruct an ImageNet test set with higher resolution to explore the effect of JPEG compression under novel Q-tables. We attempt several approaches to tune a Q-table for a vision task. We find that a simple sorted random sampling method can exceed the performance of the standard JPEG Q-table. We also use hyper-parameter tuning techniques including bounded random search, Bayesian optimization, and composite heuristic optimization methods. The new Q-tables we obtained can improve the compression rate by 10% to 200% when the accuracy is fixed, or improve accuracy up to $2\%$ at the same compression rate.
In this paper, we propose a Hierarchical Learned Video Compression (HLVC) method with three hierarchical quality layers and a recurrent enhancement network. The frames in the first layer are compressed by an image compression method with the highest quality. Using these frames as references, we propose the Bi-Directional Deep Compression (BDDC) network to compress the second layer with relatively high quality. Then, the third layer frames are compressed with the lowest quality, by the proposed Single Motion Deep Compression (SMDC) network, which adopts a single motion map to estimate the motions of multiple frames, thus saving bits for motion information. In our deep decoder, we develop the Weighted Recurrent Quality Enhancement (WRQE) network, which takes both compressed frames and the bit stream as inputs. In the recurrent cell of WRQE, the memory and update signal are weighted by quality features to reasonably leverage multi-frame information for enhancement. In our HLVC approach, the hierarchical quality benefits the coding efficiency, since the high quality information facilitates the compression and enhancement of low quality frames at encoder and decoder sides, respectively. Finally, the experiments validate that our HLVC approach advances the state-of-the-art of deep video compression methods, and outperforms the "Low-Delay P (LDP) very fast" mode of x265 in terms of both PSNR and MS-SSIM. The project page is at https://github.com/RenYang-home/HLVC.
With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of rate-distortion performance. However, continuous rate adaptation remains an open question. Some learned image compression methods use multiple networks for multiple rates, while others use one single model at the expense of computational complexity increase and performance degradation. In this paper, we propose a continuously rate adjustable learned image compression framework, Asymmetric Gained Variational Autoencoder (AG-VAE). AG-VAE utilizes a pair of gain units to achieve discrete rate adaptation in one single model with a negligible additional computation. Then, by using exponential interpolation, continuous rate adaptation is achieved without compromising performance. Besides, we propose the asymmetric Gaussian entropy model for more accurate entropy estimation. Exhaustive experiments show that our method achieves comparable quantitative performance with SOTA learned image compression methods and better qualitative performance than classical image codecs. In the ablation study, we confirm the usefulness and superiority of gain units and the asymmetric Gaussian entropy model.